localminimum / R-net

A Tensorflow Implementation of R-net: Machine reading comprehension with self matching networks
MIT License
323 stars 122 forks source link

Training restarted again after it hit 100% #42

Open rajdeinno opened 5 years ago

rajdeinno commented 5 years ago

Initially I had issue while running model.py. Cannot reshape array of size 27481400 into shape(91604,300).

But I have fixed it by changing the config value vocab_size by 2196018 .

My training has started successfully after the above config change. It was running around 5 days and completed 100 %. I left my machine open for training and I thought it will end up after 100%. But yesterday again it started to run from the scratch. Any issue here? or do I need to stop manually when it comes to 100%?

I set num_epochs to 10 in params.py file. Will it run for 10 cycles?

I have attached screen shot. Any help would be really appreciated R-Net rerun issue .

I have VM with 64 GB RAM and I am using Ubuntu 14.04.